Merge tag 'block-5.15-2021-10-29' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request:
      - fix nvmet-tcp header digest verification (Amit Engel)
      - fix a memory leak in nvmet-tcp when releasing a queue (Maurizio
        Lombardi)
      - fix nvme-tcp H2CData PDU send accounting again (Sagi Grimberg)
      - fix digest pointer calculation in nvme-tcp and nvmet-tcp (Varun
        Prakash)
      - fix possible nvme-tcp req->offset corruption (Varun Prakash)

 - Queue drain ordering fix (Ming)

 - Partition check regression for zoned devices (Shin'ichiro)

 - Zone queue restart fix (Naohiro)

* tag 'block-5.15-2021-10-29' of git://git.kernel.dk/linux-block:
  block: Fix partition check for host-aware zoned block devices
  nvmet-tcp: fix header digest verification
  nvmet-tcp: fix data digest pointer calculation
  nvme-tcp: fix data digest pointer calculation
  nvme-tcp: fix possible req->offset corruption
  block: schedule queue restart after BLK_STS_ZONE_RESOURCE
  block: drain queue after disk is removed from sysfs
  nvme-tcp: fix H2CData PDU send accounting (again)
  nvmet-tcp: fix a memory leak when releasing a queue

Author: torvalds

block/blk-mq.c

@@ -1325,6 +1325,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	int errors, queued;
 	blk_status_t ret = BLK_STS_OK;
 	LIST_HEAD(zone_list);
+	bool needs_resource = false;
 
 	if (list_empty(list))
 		return false;
@@ -1370,6 +1371,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			queued++;
 			break;
 		case BLK_STS_RESOURCE:
+			needs_resource = true;
+			fallthrough;
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
@@ -1380,6 +1383,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 			 * accept.
 			 */
 			blk_mq_handle_zone_resource(rq, &zone_list);
+			needs_resource = true;
 			break;
 		default:
 			errors++;
@@ -1406,7 +1410,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		/* For non-shared tags, the RESTART check will suffice */
 		bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
 			(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
-		bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
 
 		if (nr_budgets)
 			blk_mq_release_budgets(q, list);
@@ -1447,14 +1450,16 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		 * If driver returns BLK_STS_RESOURCE and SCHED_RESTART
 		 * bit is set, run queue after a delay to avoid IO stalls
 		 * that could otherwise occur if the queue is idle.  We'll do
-		 * similar if we couldn't get budget and SCHED_RESTART is set.
+		 * similar if we couldn't get budget or couldn't lock a zone
+		 * and SCHED_RESTART is set.
 		 */
 		needs_restart = blk_mq_sched_needs_restart(hctx);
+		if (prep == PREP_DISPATCH_NO_BUDGET)
+			needs_resource = true;
 		if (!needs_restart ||
 		    (no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
 			blk_mq_run_hw_queue(hctx, true);
-		else if (needs_restart && (ret == BLK_STS_RESOURCE ||
-					   no_budget_avail))
+		else if (needs_restart && needs_resource)
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
 		blk_mq_update_dispatch_busy(hctx, true);

block/blk-settings.c

@@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
+static bool disk_has_partitions(struct gendisk *disk)
+{
+	unsigned long idx;
+	struct block_device *part;
+	bool ret = false;
+
+	rcu_read_lock();
+	xa_for_each(&disk->part_tbl, idx, part) {
+		if (bdev_is_partition(part)) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /**
  * blk_queue_set_zoned - configure a disk queue zoned model.
  * @disk:	the gendisk of the queue to configure
@@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 		 * we do nothing special as far as the block layer is concerned.
 		 */
 		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    !xa_empty(&disk->part_tbl))
+		    disk_has_partitions(disk))
 			model = BLK_ZONED_NONE;
 		break;
 	case BLK_ZONED_NONE:

block/genhd.c

@@ -588,16 +588,6 @@ void del_gendisk(struct gendisk *disk)
 	 * Prevent new I/O from crossing bio_queue_enter().
 	 */
 	blk_queue_start_drain(q);
-	blk_mq_freeze_queue_wait(q);
-
-	rq_qos_exit(q);
-	blk_sync_queue(q);
-	blk_flush_integrity();
-	/*
-	 * Allow using passthrough request again after the queue is torn down.
-	 */
-	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
-	__blk_mq_unfreeze_queue(q, true);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -620,6 +610,18 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
+
+	blk_mq_freeze_queue_wait(q);
+
+	rq_qos_exit(q);
+	blk_sync_queue(q);
+	blk_flush_integrity();
+	/*
+	 * Allow using passthrough request again after the queue is torn down.
+	 */
+	blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+	__blk_mq_unfreeze_queue(q, true);
+
 }
 EXPORT_SYMBOL(del_gendisk);
 

drivers/nvme/host/tcp.c

@@ -926,12 +926,14 @@ static void nvme_tcp_fail_request(struct nvme_tcp_request *req)
 static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
+	int req_data_len = req->data_len;
 
 	while (true) {
 		struct page *page = nvme_tcp_req_cur_page(req);
 		size_t offset = nvme_tcp_req_cur_offset(req);
 		size_t len = nvme_tcp_req_cur_length(req);
 		bool last = nvme_tcp_pdu_last_send(req, len);
+		int req_data_sent = req->data_sent;
 		int ret, flags = MSG_DONTWAIT;
 
 		if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
@@ -958,7 +960,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		 * in the request where we don't want to modify it as we may
 		 * compete with the RX path completing the request.
 		 */
-		if (req->data_sent + ret < req->data_len)
+		if (req_data_sent + ret < req_data_len)
 			nvme_tcp_advance_req(req, ret);
 
 		/* fully successful last send in current PDU */
@@ -1048,10 +1050,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
 static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
 {
 	struct nvme_tcp_queue *queue = req->queue;
+	size_t offset = req->offset;
 	int ret;
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
 	struct kvec iov = {
-		.iov_base = &req->ddgst + req->offset,
+		.iov_base = (u8 *)&req->ddgst + req->offset,
 		.iov_len = NVME_TCP_DIGEST_LENGTH - req->offset
 	};
 
@@ -1064,7 +1067,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
 	if (unlikely(ret <= 0))
 		return ret;
 
-	if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) {
+	if (offset + ret == NVME_TCP_DIGEST_LENGTH) {
 		nvme_tcp_done_send_req(queue);
 		return 1;
 	}

drivers/nvme/target/tcp.c

@@ -702,7 +702,7 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
 	struct nvmet_tcp_queue *queue = cmd->queue;
 	struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
 	struct kvec iov = {
-		.iov_base = &cmd->exp_ddgst + cmd->offset,
+		.iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
 		.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
 	};
 	int ret;
@@ -1096,7 +1096,7 @@ static int nvmet_tcp_try_recv_pdu(struct nvmet_tcp_queue *queue)
 	}
 
 	if (queue->hdr_digest &&
-	    nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) {
+	    nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) {
 		nvmet_tcp_fatal_error(queue); /* fatal */
 		return -EPROTO;
 	}
@@ -1428,6 +1428,7 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
 
 static void nvmet_tcp_release_queue_work(struct work_struct *w)
 {
+	struct page *page;
 	struct nvmet_tcp_queue *queue =
 		container_of(w, struct nvmet_tcp_queue, release_work);
 
@@ -1447,6 +1448,8 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
 		nvmet_tcp_free_crypto(queue);
 	ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
 
+	page = virt_to_head_page(queue->pf_cache.va);
+	__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
 	kfree(queue);
 }